Aller au contenu
Menu
Français

Stack recommandé

Que construisez-vous ? Semantic search

Une technologie par emplacement, avec la raison de la suggestion et par quoi la remplacer.

Embedding

concept

Embedding

Dense numeric vector representing the meaning of a piece of text.

Why editorial

Everything else in semantic search depends on the quality of the embedding: a weak one makes good ranking impossible.

Vector database

database

Weaviate

Open-source vector database with hybrid keyword and vector search built in.

Why déduit du graphe

Weaviate uses Embedding

Source

Base model

model

BERT

Encoder-only Transformer pre-trained with masked language modelling.

Why déduit du graphe

Reranking based on BERT

Source

Reranking

technique

Reranking

Second-stage ordering of retrieved candidates by a more accurate scoring model.

Why déduit du graphe

Retrieve-then-rerank is the standard shape of a semantic search pipeline.

Source